Skip to content
inetGeek

DeepInfra pricing and limits

iScore46–63 · ≈#6/10
deepinfra.com · LLM APIs
SEPT 2026 audit

Serverless inference for open-weight models with published cached-input rates, plus dedicated GPUs billed by the minute.

Visit DeepInfra documentation

No affiliate links, sponsored placements or paid rankings appear on this site. Ordering follows the sourced data and the stated criteria.

Entry paid planNo minimum spend and no seat fees - billing is pay-per-token usage only, with no charge for idle GPU time.
RegionsServerless inference runs on DeepInfra's own inference-optimised infrastructure in US-based data centers. No region selector is documented for the shared inference API.
Free tierNo
CategoryLLM APIs

Reviewed by Palash BagchiUpdated 23 criteria comparedSources last checked

DeepInfra pricing at a glance

Entry paid plan
No minimum spend and no seat fees - billing is pay-per-token usage only, with no charge for idle GPU time source ↗
Pricing model
Two products on one bill: per-token serverless inference with a separate cached-input rate for each model, and dedicated GPUs billed per… source ↗

First line of each sourced value. The full text is in DeepInfra pricing below.

01.Evaluation guide

Who it suits

Running open-weight models at the lowest published per-token rates here — DeepSeek-V4-Flash at $0.06 per million input is a fraction of what the lab itself charges — with dedicated H100s at $2.20 an hour if throughput demands it.

Consider something else if…

Only some models carry per-token pricing; the rest bill for inference execution time, which is a different and harder thing to forecast.

Editorial · Palash Bagchi · approved

Machine-derived signals

Not sourced facts — counts and matches read by a script, not a person. See each line for where it comes from.

DeepInfra's own site (deepinfra.com) self-detects as: hosting — Cloud PaaS, Cloud Hosting, US hosting, Server Location · DNS — Enterprise DNS (category-level via BuiltWith, not a named vendor)

Each value below links to the page it was read from, with the sentence it came from. Criteria DeepInfra does not publish are not listed.

DeepInfra pricing

5 criteria
Free tierNo
Sources (1) →
Kind of free offerNo free offer
Sources (1) →
Credit card to startYes
Sources (1) →
Entry paid planNo minimum spend and no seat fees - billing is pay-per-token usage only, with no charge for idle GPU time.
Sources (1) →
Pricing modelTwo products on one bill: per-token serverless inference with a separate cached-input rate for each model, and dedicated GPUs billed per minute and invoiced weekly. Models without per-token pricing are billed for inference execution time instead.
Sources (1) →
  • Pricing — DeepInfra ↗

    “Some of our langauge models offer per token pricing. Most other models are billed for inference execution time. [...] Billed in minute granularity Invoiced weekly”

    Read 2026-09-06 · official pricing · Report a correction

Infrastructure

1 criteria
RegionsServerless inference runs on DeepInfra's own inference-optimised infrastructure in US-based data centers. No region selector is documented for the shared inference API.
Sources (1) →

Inference

8 criteria
Input price, top model$1.30 per million input tokens for DeepSeek-V4-Pro, the most expensive model in its catalogue. Cached input is $0.10.
Sources (1) →
Output price, top model$2.60 per million output tokens for DeepSeek-V4-Pro.
Sources (1) →
Input price, cheapest model$0.06 per million input tokens for DeepSeek-V4-Flash-0731, with cached input at $0.015 and output at $0.18. DeepSeek itself charges $0.44 at peak for the same checkpoint and Fireworks $0.22.
Sources (1) →
Context window1024k tokens on the DeepSeek V4 models it serves; 160k on the V3 generation. The window is the model's rather than a platform limit.
Sources (1) →
Max output tokensHard cap of 16384 output tokens per response for most models on the chat completions API; the exact limit is model-dependent.
Sources (1) →
Prompt cachingSupported
Sources (1) →
Batch discountBatch API jobs are billed 20% below real-time pricing, with results returned within 24 hours.
Sources (1) →
Rate limitsDefault 200 concurrent requests per model per account (429 above it); a limit increase can be requested in the dashboard.
Sources (1) →

GPU

2 criteria
H100 SXM, per GPU-hour$2.20 per GPU-hour for a dedicated H100 80GB — below every dedicated cloud in this dataset. A100 80GB is $0.89, H200 $2.69, B200 $3.69. Billed in minute granularity, invoiced weekly.
Sources (1) →
  • Pricing — DeepInfra ↗

    “A100 80GB $0.89 / GPU-hour H100 80GB $2.20 / GPU-hour H200 141GB $2.69 / GPU-hour B200 180GB $3.69 / GPU-hour B300 270GB $4.89 / GPU-hour [...] Billed in minute granularity Invoiced weekly”

    Read 2026-09-06 · official pricing · Report a correction

Largest GPU offered270GB per GPU on a B300, at $4.89 per GPU-hour.
Sources (1) →

Compliance

7 criteria
SOC 2Security measures stated to comply with SOC 2 standards in the privacy policy; no report, audit type or auditor is published.
Sources (1) →
ISO 27001Security measures stated to comply with ISO 27001 standards in the privacy policy; no certificate or issuing body is published.
Sources (1) →
HIPAATechnical and organizational measures for HIPAA compliance stated in the privacy policy; no BAA or eligible-services list is published.
Sources (1) →
GDPR / data residencyPrivacy Policy: data may be transferred, stored and processed outside your jurisdiction, specifically in the United States; EU residents keep GDPR rights.
Sources (1) →
  • DeepInfra Privacy Policy ↗

    “Your data may be transferred, stored, and processed outside of your jurisdiction, specifically in the United States. [...] If you are a resident of the European Union you may have additional rights under the General Data Protection Regulation.”

    Read 2026-09-13 · official site · Report a correction

Encryption at restInference inputs and outputs are not stored to disk; bulk-inference data may be stored on disk in encrypted form, then deleted.
Sources (1) →
Role-based access controlTeam roles are member and admin; an admin can change roles, but all team members share the same API tokens and models.
Sources (1) →
  • Okta SSO - DeepInfra ↗

    “Admin can change team member roles (member / admin) [...] All team members share the same API tokens and models [...] For per-user isolation (separate tokens and models per person), contact us”

    Read 2026-09-13 · official docs · Report a correction

Dedicated infrastructurePrivate model deployments run on dedicated GPU infrastructure - your weights, your endpoint, your isolation - not shared with other users.
Sources (1) →

When these numbers change, hear about it. Sources are re-checked monthly; a repricing goes out as a short note.

Confirm by email; unsubscribe from any issue. Your address goes to Kit and nowhere else — what we do with it.

DeepInfra in the news

Headlines from other publications, not checked by us · collected

Selected by a search on this company, refreshed weekly. Nobody here has verified these claims — where something material is confirmed, it is written into the page above with its source, the way every other fact on this site is.

DeepInfra pricing questions

How much does DeepInfra cost?

No minimum spend and no seat fees - billing is pay-per-token usage only, with no charge for idle GPU time.

What is DeepInfra - DeepInfra · read

How does DeepInfra charge?

Two products on one bill: per-token serverless inference with a separate cached-input rate for each model, and dedicated GPUs billed per minute and invoiced weekly. Models without per-token pricing are billed for inference execution time instead.

Pricing — DeepInfra · read

Does DeepInfra have a free tier?

No.

Simple Pricing | Machine Learning Infrastructure | DeepInfra · read

Do you need a credit card to start on DeepInfra?

Yes.

DeepInfra Pricing · read

Comments

Every page here is sourced and dated.